Skip to content

Benchmark

MentalHealthBench · Behavior · Reality-testing calibration

Scores are percentages. Higher is better.

Models and systems measured
15
Scores recorded
15
Sources
1
IQ weight
0.63

Score distribution

68%
Mean
65.5%
Median
14%
Std dev
49.2%
10th percentile
87.2%
90th percentile
42.2%
Min
42.2%91.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.63 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1GPT-6 AstraOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.7%
2GPT-6 SolOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87.2%
3GPT-6 LunaOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.9%
4Claude Opus 5.5OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs72.5%
5Grok 4.7OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs71.4%
6Claude Haiku 4.5OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs65.5%
7Claude Sonnet 5OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs65.3%
8Claude Fable 5.1OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs64.1%
9Gemini 3.8 FlashOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs59.4%
10Muse Spark 1.3OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs55%
11Gemini 3.1 Pro PreviewOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs49.2%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Gemini 2.5 ProOpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs42.2%
GPT-4o (March 2025)OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.8%
GPT-5.6 Luna (Aug 2026)OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.8%
GPT-5.6 Sol (Aug 2026)OpenAI evaluation · 95% CI available on source page· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.7%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.